Merge tag 'powerpc-4.3-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:

 - support "hybrid" iommu/direct DMA ops for coherent_mask < dma_mask
   from Benjamin Herrenschmidt

 - EEH fixes for SRIOV from Gavin

 - introduce rtas_get_sensor_fast() for IRQ handlers from Thomas Huth

 - use hardware RNG for arch_get_random_seed_* not arch_get_random_*
   from Paul Mackerras

 - seccomp filter support from Michael Ellerman

 - opal_cec_reboot2() handling for HMIs & machine checks from Mahesh
   Salgaonkar

 - add powerpc timebase as a trace clock source from Naveen N.  Rao

 - misc cleanups in the xmon, signal & SLB code from Anshuman Khandual

 - add an inline function to update POWER8 HID0 from Gautham R.  Shenoy

 - fix pte_pagesize_index() crash on 4K w/64K hash from Michael Ellerman

 - drop support for 64K local store on 4K kernels from Michael Ellerman

 - move dma_get_required_mask() from pnv_phb to pci_controller_ops from
   Andrew Donnellan

 - initialize distance lookup table from drconf path from Nikunj A
   Dadhania

 - enable RTC class support from Vaibhav Jain

 - disable automatically blocked PCI config from Gavin Shan

 - add LEDs driver for PowerNV platform from Vasant Hegde

 - fix endianness issues in the HVSI driver from Laurent Dufour

 - kexec endian fixes from Samuel Mendoza-Jonas

 - fix corrupted pdn list from Gavin Shan

 - fix fenced PHB caused by eeh_slot_error_detail() from Gavin Shan

 - Freescale updates from Scott: Highlights include 32-bit memcpy/memset
   optimizations, checksum optimizations, 85xx config fragments and
   updates, device tree updates, e6500 fixes for non-SMP, and misc
   cleanup and minor fixes.

 - a ton of cxl updates & fixes:
    - add explicit precision specifiers from Rasmus Villemoes
    - use more common format specifier from Rasmus Villemoes
    - destroy cxl_adapter_idr on module_exit from Johannes Thumshirn
    - destroy afu->contexts_idr on release of an afu from Johannes
      Thumshirn
    - compile with -Werror from Daniel Axtens
    - EEH support from Daniel Axtens
    - plug irq_bitmap getting leaked in cxl_context from Vaibhav Jain
    - add alternate MMIO error handling from Ian Munsie
    - allow release of contexts which have been OPENED but not STARTED
      from Andrew Donnellan
    - remove use of macro DEFINE_PCI_DEVICE_TABLE from Vaishali Thakkar
    - release irqs if memory allocation fails from Vaibhav Jain
    - remove racy attempt to force EEH invocation in reset from Daniel
      Axtens
    - fix + cleanup error paths in cxl_dev_context_init from Ian Munsie
    - fix force unmapping mmaps of contexts allocated through the kernel
      api from Ian Munsie
    - set up and enable PSL Timebase from Philippe Bergheaud

* tag 'powerpc-4.3-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (140 commits)
  cxl: Set up and enable PSL Timebase
  cxl: Fix force unmapping mmaps of contexts allocated through the kernel api
  cxl: Fix + cleanup error paths in cxl_dev_context_init
  powerpc/eeh: Fix fenced PHB caused by eeh_slot_error_detail()
  powerpc/pseries: Cleanup on pci_dn_reconfig_notifier()
  powerpc/pseries: Fix corrupted pdn list
  powerpc/powernv: Enable LEDS support
  powerpc/iommu: Set default DMA offset in dma_dev_setup
  cxl: Remove racy attempt to force EEH invocation in reset
  cxl: Release irqs if memory allocation fails
  cxl: Remove use of macro DEFINE_PCI_DEVICE_TABLE
  powerpc/powernv: Fix mis-merge of OPAL support for LEDS driver
  powerpc/powernv: Reset HILE before kexec_sequence()
  powerpc/kexec: Reset secondary cpu endianness before kexec
  powerpc/hvsi: Fix endianness issues in the HVSI driver
  leds/powernv: Add driver for PowerNV platform
  powerpc/powernv: Create LED platform device
  powerpc/powernv: Add OPAL interfaces for accessing and modifying system LED states
  powerpc/powernv: Fix the log message when disabling VF
  cxl: Allow release of contexts which have been OPENED but not STARTED
  ...

14 files changed, 865 insertions, 205 deletions

diff --git a/drivers/misc/cxl/Kconfig b/drivers/misc/cxl/Kconfig
index b6db9ebd52c2..8756d06e2bb8 100644
--- a/drivers/misc/cxl/Kconfig
+++ b/drivers/misc/cxl/Kconfig
@@ -11,11 +11,16 @@ config CXL_KERNEL_API
 	bool
 	default n
 
+config CXL_EEH
+	bool
+	default n
+
 config CXL
 	tristate "Support for IBM Coherent Accelerators (CXL)"
-	depends on PPC_POWERNV && PCI_MSI
+	depends on PPC_POWERNV && PCI_MSI && EEH
 	select CXL_BASE
 	select CXL_KERNEL_API
+	select CXL_EEH
 	default m
 	help
 	  Select this option to enable driver support for IBM Coherent
diff --git a/drivers/misc/cxl/Makefile b/drivers/misc/cxl/Makefile
index 14e3f8219a11..6f484dfe78f9 100644
--- a/drivers/misc/cxl/Makefile
+++ b/drivers/misc/cxl/Makefile
@@ -1,3 +1,5 @@
+ccflags-y := -Werror
+
 cxl-y				+= main.o file.o irq.o fault.o native.o
 cxl-y				+= context.o sysfs.o debugfs.o pci.o trace.o
 cxl-y				+= vphb.o api.o
diff --git a/drivers/misc/cxl/api.c b/drivers/misc/cxl/api.c
index 729e0851167d..8af12c884b04 100644
--- a/drivers/misc/cxl/api.c
+++ b/drivers/misc/cxl/api.c
@@ -12,11 +12,13 @@
 #include <linux/anon_inodes.h>
 #include <linux/file.h>
 #include <misc/cxl.h>
+#include <linux/fs.h>
 
 #include "cxl.h"
 
 struct cxl_context *cxl_dev_context_init(struct pci_dev *dev)
 {
+	struct address_space *mapping;
 	struct cxl_afu *afu;
 	struct cxl_context  *ctx;
 	int rc;
@@ -25,19 +27,42 @@ struct cxl_context *cxl_dev_context_init(struct pci_dev *dev)
 
 	get_device(&afu->dev);
 	ctx = cxl_context_alloc();
-	if (IS_ERR(ctx))
-		return ctx;
+	if (IS_ERR(ctx)) {
+		rc = PTR_ERR(ctx);
+		goto err_dev;
+	}
 
-	/* Make it a slave context.  We can promote it later? */
-	rc = cxl_context_init(ctx, afu, false, NULL);
-	if (rc) {
-		kfree(ctx);
-		put_device(&afu->dev);
-		return ERR_PTR(-ENOMEM);
+	ctx->kernelapi = true;
+
+	/*
+	 * Make our own address space since we won't have one from the
+	 * filesystem like the user api has, and even if we do associate a file
+	 * with this context we don't want to use the global anonymous inode's
+	 * address space as that can invalidate unrelated users:
+	 */
+	mapping = kmalloc(sizeof(struct address_space), GFP_KERNEL);
+	if (!mapping) {
+		rc = -ENOMEM;
+		goto err_ctx;
 	}
+	address_space_init_once(mapping);
+
+	/* Make it a slave context.  We can promote it later? */
+	rc = cxl_context_init(ctx, afu, false, mapping);
+	if (rc)
+		goto err_mapping;
+
 	cxl_assign_psn_space(ctx);
 
 	return ctx;
+
+err_mapping:
+	kfree(mapping);
+err_ctx:
+	kfree(ctx);
+err_dev:
+	put_device(&afu->dev);
+	return ERR_PTR(rc);
 }
 EXPORT_SYMBOL_GPL(cxl_dev_context_init);
 
@@ -59,7 +84,7 @@ EXPORT_SYMBOL_GPL(cxl_get_phys_dev);
 
 int cxl_release_context(struct cxl_context *ctx)
 {
-	if (ctx->status != CLOSED)
+	if (ctx->status >= STARTED)
 		return -EBUSY;
 
 	put_device(&ctx->afu->dev);
@@ -255,9 +280,16 @@ struct file *cxl_get_fd(struct cxl_context *ctx, struct file_operations *fops,
 
 	file = anon_inode_getfile("cxl", fops, ctx, flags);
 	if (IS_ERR(file))
-		put_unused_fd(fdtmp);
+		goto err_fd;
+
+	file->f_mapping = ctx->mapping;
+
 	*fd = fdtmp;
 	return file;
+
+err_fd:
+	put_unused_fd(fdtmp);
+	return NULL;
 }
 EXPORT_SYMBOL_GPL(cxl_get_fd);
 
@@ -327,3 +359,10 @@ int cxl_afu_reset(struct cxl_context *ctx)
 	return cxl_afu_check_and_enable(afu);
 }
 EXPORT_SYMBOL_GPL(cxl_afu_reset);
+
+void cxl_perst_reloads_same_image(struct cxl_afu *afu,
+				  bool perst_reloads_same_image)
+{
+	afu->adapter->perst_same_image = perst_reloads_same_image;
+}
+EXPORT_SYMBOL_GPL(cxl_perst_reloads_same_image);
diff --git a/drivers/misc/cxl/context.c b/drivers/misc/cxl/context.c
index 1287148629c0..e762f85ee233 100644
--- a/drivers/misc/cxl/context.c
+++ b/drivers/misc/cxl/context.c
@@ -126,6 +126,18 @@ static int cxl_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	if (ctx->status != STARTED) {
 		mutex_unlock(&ctx->status_mutex);
 		pr_devel("%s: Context not started, failing problem state access\n", __func__);
+		if (ctx->mmio_err_ff) {
+			if (!ctx->ff_page) {
+				ctx->ff_page = alloc_page(GFP_USER);
+				if (!ctx->ff_page)
+					return VM_FAULT_OOM;
+				memset(page_address(ctx->ff_page), 0xff, PAGE_SIZE);
+			}
+			get_page(ctx->ff_page);
+			vmf->page = ctx->ff_page;
+			vma->vm_page_prot = pgprot_cached(vma->vm_page_prot);
+			return 0;
+		}
 		return VM_FAULT_SIGBUS;
 	}
 
@@ -193,7 +205,11 @@ int __detach_context(struct cxl_context *ctx)
 	if (status != STARTED)
 		return -EBUSY;
 
-	WARN_ON(cxl_detach_process(ctx));
+	/* Only warn if we detached while the link was OK.
+	 * If detach fails when hw is down, we don't care.
+	 */
+	WARN_ON(cxl_detach_process(ctx) &&
+		cxl_adapter_link_ok(ctx->afu->adapter));
 	flush_work(&ctx->fault_work); /* Only needed for dedicated process */
 	put_pid(ctx->pid);
 	cxl_ctx_put();
@@ -253,7 +269,11 @@ static void reclaim_ctx(struct rcu_head *rcu)
 	struct cxl_context *ctx = container_of(rcu, struct cxl_context, rcu);
 
 	free_page((u64)ctx->sstp);
+	if (ctx->ff_page)
+		__free_page(ctx->ff_page);
 	ctx->sstp = NULL;
+	if (ctx->kernelapi)
+		kfree(ctx->mapping);
 
 	kfree(ctx);
 }
diff --git a/drivers/misc/cxl/cxl.h b/drivers/misc/cxl/cxl.h
index 4fd66cabde1e..1c30ef77073d 100644
--- a/drivers/misc/cxl/cxl.h
+++ b/drivers/misc/cxl/cxl.h
@@ -34,7 +34,7 @@ extern uint cxl_verbose;
  * Bump version each time a user API change is made, whether it is
  * backwards compatible ot not.
  */
-#define CXL_API_VERSION 1
+#define CXL_API_VERSION 2
 #define CXL_API_VERSION_COMPATIBLE 1
 
 /*
@@ -83,8 +83,10 @@ static const cxl_p1_reg_t CXL_PSL_AFUSEL  = {0x00B0};
 /* 0x00C0:7EFF Implementation dependent area */
 static const cxl_p1_reg_t CXL_PSL_FIR1      = {0x0100};
 static const cxl_p1_reg_t CXL_PSL_FIR2      = {0x0108};
+static const cxl_p1_reg_t CXL_PSL_Timebase  = {0x0110};
 static const cxl_p1_reg_t CXL_PSL_VERSION   = {0x0118};
 static const cxl_p1_reg_t CXL_PSL_RESLCKTO  = {0x0128};
+static const cxl_p1_reg_t CXL_PSL_TB_CTLSTAT = {0x0140};
 static const cxl_p1_reg_t CXL_PSL_FIR_CNTL  = {0x0148};
 static const cxl_p1_reg_t CXL_PSL_DSNDCTL   = {0x0150};
 static const cxl_p1_reg_t CXL_PSL_SNWRALLOC = {0x0158};
@@ -152,6 +154,9 @@ static const cxl_p2n_reg_t CXL_PSL_WED_An     = {0x0A0};
 #define CXL_PSL_SPAP_Size_Shift 4
 #define CXL_PSL_SPAP_V    0x0000000000000001ULL
 
+/****** CXL_PSL_Control ****************************************************/
+#define CXL_PSL_Control_tb 0x0000000000000001ULL
+
 /****** CXL_PSL_DLCNTL *****************************************************/
 #define CXL_PSL_DLCNTL_D (0x1ull << (63-28))
 #define CXL_PSL_DLCNTL_C (0x1ull << (63-29))
@@ -418,6 +423,9 @@ struct cxl_context {
 	/* Used to unmap any mmaps when force detaching */
 	struct address_space *mapping;
 	struct mutex mapping_lock;
+	struct page *ff_page;
+	bool mmio_err_ff;
+	bool kernelapi;
 
 	spinlock_t sste_lock; /* Protects segment table entries */
 	struct cxl_sste *sstp;
@@ -493,6 +501,7 @@ struct cxl {
 	bool user_image_loaded;
 	bool perst_loads_image;
 	bool perst_select_user;
+	bool perst_same_image;
 };
 
 int cxl_alloc_one_irq(struct cxl *adapter);
@@ -531,16 +540,33 @@ struct cxl_process_element {
 	__be32 software_state;
 } __packed;
 
+static inline bool cxl_adapter_link_ok(struct cxl *cxl)
+{
+	struct pci_dev *pdev;
+
+	pdev = to_pci_dev(cxl->dev.parent);
+	return !pci_channel_offline(pdev);
+}
+
 static inline void __iomem *_cxl_p1_addr(struct cxl *cxl, cxl_p1_reg_t reg)
 {
 	WARN_ON(!cpu_has_feature(CPU_FTR_HVMODE));
 	return cxl->p1_mmio + cxl_reg_off(reg);
 }
 
-#define cxl_p1_write(cxl, reg, val) \
-	out_be64(_cxl_p1_addr(cxl, reg), val)
-#define cxl_p1_read(cxl, reg) \
-	in_be64(_cxl_p1_addr(cxl, reg))
+static inline void cxl_p1_write(struct cxl *cxl, cxl_p1_reg_t reg, u64 val)
+{
+	if (likely(cxl_adapter_link_ok(cxl)))
+		out_be64(_cxl_p1_addr(cxl, reg), val);
+}
+
+static inline u64 cxl_p1_read(struct cxl *cxl, cxl_p1_reg_t reg)
+{
+	if (likely(cxl_adapter_link_ok(cxl)))
+		return in_be64(_cxl_p1_addr(cxl, reg));
+	else
+		return ~0ULL;
+}
 
 static inline void __iomem *_cxl_p1n_addr(struct cxl_afu *afu, cxl_p1n_reg_t reg)
 {
@@ -548,26 +574,56 @@ static inline void __iomem *_cxl_p1n_addr(struct cxl_afu *afu, cxl_p1n_reg_t reg
 	return afu->p1n_mmio + cxl_reg_off(reg);
 }
 
-#define cxl_p1n_write(afu, reg, val) \
-	out_be64(_cxl_p1n_addr(afu, reg), val)
-#define cxl_p1n_read(afu, reg) \
-	in_be64(_cxl_p1n_addr(afu, reg))
+static inline void cxl_p1n_write(struct cxl_afu *afu, cxl_p1n_reg_t reg, u64 val)
+{
+	if (likely(cxl_adapter_link_ok(afu->adapter)))
+		out_be64(_cxl_p1n_addr(afu, reg), val);
+}
+
+static inline u64 cxl_p1n_read(struct cxl_afu *afu, cxl_p1n_reg_t reg)
+{
+	if (likely(cxl_adapter_link_ok(afu->adapter)))
+		return in_be64(_cxl_p1n_addr(afu, reg));
+	else
+		return ~0ULL;
+}
 
 static inline void __iomem *_cxl_p2n_addr(struct cxl_afu *afu, cxl_p2n_reg_t reg)
 {
 	return afu->p2n_mmio + cxl_reg_off(reg);
 }
 
-#define cxl_p2n_write(afu, reg, val) \
-	out_be64(_cxl_p2n_addr(afu, reg), val)
-#define cxl_p2n_read(afu, reg) \
-	in_be64(_cxl_p2n_addr(afu, reg))
+static inline void cxl_p2n_write(struct cxl_afu *afu, cxl_p2n_reg_t reg, u64 val)
+{
+	if (likely(cxl_adapter_link_ok(afu->adapter)))
+		out_be64(_cxl_p2n_addr(afu, reg), val);
+}
+
+static inline u64 cxl_p2n_read(struct cxl_afu *afu, cxl_p2n_reg_t reg)
+{
+	if (likely(cxl_adapter_link_ok(afu->adapter)))
+		return in_be64(_cxl_p2n_addr(afu, reg));
+	else
+		return ~0ULL;
+}
 
+static inline u64 cxl_afu_cr_read64(struct cxl_afu *afu, int cr, u64 off)
+{
+	if (likely(cxl_adapter_link_ok(afu->adapter)))
+		return in_le64((afu)->afu_desc_mmio + (afu)->crs_offset +
+			       ((cr) * (afu)->crs_len) + (off));
+	else
+		return ~0ULL;
+}
 
-#define cxl_afu_cr_read64(afu, cr, off) \
-	in_le64((afu)->afu_desc_mmio + (afu)->crs_offset + ((cr) * (afu)->crs_len) + (off))
-#define cxl_afu_cr_read32(afu, cr, off) \
-	in_le32((afu)->afu_desc_mmio + (afu)->crs_offset + ((cr) * (afu)->crs_len) + (off))
+static inline u32 cxl_afu_cr_read32(struct cxl_afu *afu, int cr, u64 off)
+{
+	if (likely(cxl_adapter_link_ok(afu->adapter)))
+		return in_le32((afu)->afu_desc_mmio + (afu)->crs_offset +
+			       ((cr) * (afu)->crs_len) + (off));
+	else
+		return 0xffffffff;
+}
 u16 cxl_afu_cr_read16(struct cxl_afu *afu, int cr, u64 off);
 u8 cxl_afu_cr_read8(struct cxl_afu *afu, int cr, u64 off);
 
@@ -585,6 +641,9 @@ void unregister_cxl_calls(struct cxl_calls *calls);
 int cxl_alloc_adapter_nr(struct cxl *adapter);
 void cxl_remove_adapter_nr(struct cxl *adapter);
 
+int cxl_alloc_spa(struct cxl_afu *afu);
+void cxl_release_spa(struct cxl_afu *afu);
+
 int cxl_file_init(void);
 void cxl_file_exit(void);
 int cxl_register_adapter(struct cxl *adapter);
@@ -675,6 +734,7 @@ int cxl_psl_purge(struct cxl_afu *afu);
 
 void cxl_stop_trace(struct cxl *cxl);
 int cxl_pci_vphb_add(struct cxl_afu *afu);
+void cxl_pci_vphb_reconfigure(struct cxl_afu *afu);
 void cxl_pci_vphb_remove(struct cxl_afu *afu);
 
 extern struct pci_driver cxl_pci_driver;
diff --git a/drivers/misc/cxl/debugfs.c b/drivers/misc/cxl/debugfs.c
index 825c412580bc..18df6f44af2a 100644
--- a/drivers/misc/cxl/debugfs.c
+++ b/drivers/misc/cxl/debugfs.c
@@ -48,7 +48,7 @@ DEFINE_SIMPLE_ATTRIBUTE(fops_io_x64, debugfs_io_u64_get, debugfs_io_u64_set, "0x
 static struct dentry *debugfs_create_io_x64(const char *name, umode_t mode,
 					    struct dentry *parent, u64 __iomem *value)
 {
-	return debugfs_create_file(name, mode, parent, (void *)value, &fops_io_x64);
+	return debugfs_create_file(name, mode, parent, (void __force *)value, &fops_io_x64);
 }
 
 int cxl_debugfs_adapter_add(struct cxl *adapter)
diff --git a/drivers/misc/cxl/file.c b/drivers/misc/cxl/file.c
index e3f4b69527a9..a30bf285b5bd 100644
--- a/drivers/misc/cxl/file.c
+++ b/drivers/misc/cxl/file.c
@@ -73,6 +73,11 @@ static int __afu_open(struct inode *inode, struct file *file, bool master)
 	if (!afu->current_mode)
 		goto err_put_afu;
 
+	if (!cxl_adapter_link_ok(adapter)) {
+		rc = -EIO;
+		goto err_put_afu;
+	}
+
 	if (!(ctx = cxl_context_alloc())) {
 		rc = -ENOMEM;
 		goto err_put_afu;
@@ -179,6 +184,8 @@ static long afu_ioctl_start_work(struct cxl_context *ctx,
 	if (work.flags & CXL_START_WORK_AMR)
 		amr = work.amr & mfspr(SPRN_UAMOR);
 
+	ctx->mmio_err_ff = !!(work.flags & CXL_START_WORK_ERR_FF);
+
 	/*
 	 * We grab the PID here and not in the file open to allow for the case
 	 * where a process (master, some daemon, etc) has opened the chardev on
@@ -238,6 +245,9 @@ long afu_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	if (ctx->status == CLOSED)
 		return -EIO;
 
+	if (!cxl_adapter_link_ok(ctx->afu->adapter))
+		return -EIO;
+
 	pr_devel("afu_ioctl\n");
 	switch (cmd) {
 	case CXL_IOCTL_START_WORK:
@@ -251,7 +261,7 @@ long afu_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	return -EINVAL;
 }
 
-long afu_compat_ioctl(struct file *file, unsigned int cmd,
+static long afu_compat_ioctl(struct file *file, unsigned int cmd,
 			     unsigned long arg)
 {
 	return afu_ioctl(file, cmd, arg);
@@ -265,6 +275,9 @@ int afu_mmap(struct file *file, struct vm_area_struct *vm)
 	if (ctx->status != STARTED)
 		return -EIO;
 
+	if (!cxl_adapter_link_ok(ctx->afu->adapter))
+		return -EIO;
+
 	return cxl_context_iomap(ctx, vm);
 }
 
@@ -309,6 +322,9 @@ ssize_t afu_read(struct file *file, char __user *buf, size_t count,
 	int rc;
 	DEFINE_WAIT(wait);
 
+	if (!cxl_adapter_link_ok(ctx->afu->adapter))
+		return -EIO;
+
 	if (count < CXL_READ_MIN_SIZE)
 		return -EINVAL;
 
@@ -319,6 +335,11 @@ ssize_t afu_read(struct file *file, char __user *buf, size_t count,
 		if (ctx_event_pending(ctx))
 			break;
 
+		if (!cxl_adapter_link_ok(ctx->afu->adapter)) {
+			rc = -EIO;
+			goto out;
+		}
+
 		if (file->f_flags & O_NONBLOCK) {
 			rc = -EAGAIN;
 			goto out;
@@ -396,7 +417,7 @@ const struct file_operations afu_fops = {
 	.mmap           = afu_mmap,
 };
 
-const struct file_operations afu_master_fops = {
+static const struct file_operations afu_master_fops = {
 	.owner		= THIS_MODULE,
 	.open           = afu_master_open,
 	.poll		= afu_poll,
@@ -519,7 +540,7 @@ int __init cxl_file_init(void)
 	 * If these change we really need to update API.  Either change some
 	 * flags or update API version number CXL_API_VERSION.
 	 */
-	BUILD_BUG_ON(CXL_API_VERSION != 1);
+	BUILD_BUG_ON(CXL_API_VERSION != 2);
 	BUILD_BUG_ON(sizeof(struct cxl_ioctl_start_work) != 64);
 	BUILD_BUG_ON(sizeof(struct cxl_event_header) != 8);
 	BUILD_BUG_ON(sizeof(struct cxl_event_afu_interrupt) != 8);
diff --git a/drivers/misc/cxl/irq.c b/drivers/misc/cxl/irq.c
index 680cd263436d..583b42afeda2 100644
--- a/drivers/misc/cxl/irq.c
+++ b/drivers/misc/cxl/irq.c
@@ -30,12 +30,12 @@ static irqreturn_t handle_psl_slice_error(struct cxl_context *ctx, u64 dsisr, u6
 	serr = cxl_p1n_read(ctx->afu, CXL_PSL_SERR_An);
 	afu_debug = cxl_p1n_read(ctx->afu, CXL_AFU_DEBUG_An);
 
-	dev_crit(&ctx->afu->dev, "PSL ERROR STATUS: 0x%.16llx\n", errstat);
-	dev_crit(&ctx->afu->dev, "PSL_FIR1: 0x%.16llx\n", fir1);
-	dev_crit(&ctx->afu->dev, "PSL_FIR2: 0x%.16llx\n", fir2);
-	dev_crit(&ctx->afu->dev, "PSL_SERR_An: 0x%.16llx\n", serr);
-	dev_crit(&ctx->afu->dev, "PSL_FIR_SLICE_An: 0x%.16llx\n", fir_slice);
-	dev_crit(&ctx->afu->dev, "CXL_PSL_AFU_DEBUG_An: 0x%.16llx\n", afu_debug);
+	dev_crit(&ctx->afu->dev, "PSL ERROR STATUS: 0x%016llx\n", errstat);
+	dev_crit(&ctx->afu->dev, "PSL_FIR1: 0x%016llx\n", fir1);
+	dev_crit(&ctx->afu->dev, "PSL_FIR2: 0x%016llx\n", fir2);
+	dev_crit(&ctx->afu->dev, "PSL_SERR_An: 0x%016llx\n", serr);
+	dev_crit(&ctx->afu->dev, "PSL_FIR_SLICE_An: 0x%016llx\n", fir_slice);
+	dev_crit(&ctx->afu->dev, "CXL_PSL_AFU_DEBUG_An: 0x%016llx\n", afu_debug);
 
 	dev_crit(&ctx->afu->dev, "STOPPING CXL TRACE\n");
 	cxl_stop_trace(ctx->afu->adapter);
@@ -54,10 +54,10 @@ irqreturn_t cxl_slice_irq_err(int irq, void *data)
 	fir_slice = cxl_p1n_read(afu, CXL_PSL_FIR_SLICE_An);
 	errstat = cxl_p2n_read(afu, CXL_PSL_ErrStat_An);
 	afu_debug = cxl_p1n_read(afu, CXL_AFU_DEBUG_An);
-	dev_crit(&afu->dev, "PSL_SERR_An: 0x%.16llx\n", serr);
-	dev_crit(&afu->dev, "PSL_FIR_SLICE_An: 0x%.16llx\n", fir_slice);
-	dev_crit(&afu->dev, "CXL_PSL_ErrStat_An: 0x%.16llx\n", errstat);
-	dev_crit(&afu->dev, "CXL_PSL_AFU_DEBUG_An: 0x%.16llx\n", afu_debug);
+	dev_crit(&afu->dev, "PSL_SERR_An: 0x%016llx\n", serr);
+	dev_crit(&afu->dev, "PSL_FIR_SLICE_An: 0x%016llx\n", fir_slice);
+	dev_crit(&afu->dev, "CXL_PSL_ErrStat_An: 0x%016llx\n", errstat);
+	dev_crit(&afu->dev, "CXL_PSL_AFU_DEBUG_An: 0x%016llx\n", afu_debug);
 
 	cxl_p1n_write(afu, CXL_PSL_SERR_An, serr);
 
@@ -72,7 +72,7 @@ static irqreturn_t cxl_irq_err(int irq, void *data)
 	WARN(1, "CXL ERROR interrupt %i\n", irq);
 
 	err_ivte = cxl_p1_read(adapter, CXL_PSL_ErrIVTE);
-	dev_crit(&adapter->dev, "PSL_ErrIVTE: 0x%.16llx\n", err_ivte);
+	dev_crit(&adapter->dev, "PSL_ErrIVTE: 0x%016llx\n", err_ivte);
 
 	dev_crit(&adapter->dev, "STOPPING CXL TRACE\n");
 	cxl_stop_trace(adapter);
@@ -80,7 +80,7 @@ static irqreturn_t cxl_irq_err(int irq, void *data)
 	fir1 = cxl_p1_read(adapter, CXL_PSL_FIR1);
 	fir2 = cxl_p1_read(adapter, CXL_PSL_FIR2);
 
-	dev_crit(&adapter->dev, "PSL_FIR1: 0x%.16llx\nPSL_FIR2: 0x%.16llx\n", fir1, fir2);
+	dev_crit(&adapter->dev, "PSL_FIR1: 0x%016llx\nPSL_FIR2: 0x%016llx\n", fir1, fir2);
 
 	return IRQ_HANDLED;
 }
@@ -147,7 +147,7 @@ static irqreturn_t cxl_irq(int irq, void *data, struct cxl_irq_info *irq_info)
 	if (dsisr & CXL_PSL_DSISR_An_PE)
 		return handle_psl_slice_error(ctx, dsisr, irq_info->errstat);
 	if (dsisr & CXL_PSL_DSISR_An_AE) {
-		pr_devel("CXL interrupt: AFU Error %.llx\n", irq_info->afu_err);
+		pr_devel("CXL interrupt: AFU Error 0x%016llx\n", irq_info->afu_err);
 
 		if (ctx->pending_afu_err) {
 			/*
@@ -158,7 +158,7 @@ static irqreturn_t cxl_irq(int irq, void *data, struct cxl_irq_info *irq_info)
 			 * probably best that we log them somewhere:
 			 */
 			dev_err_ratelimited(&ctx->afu->dev, "CXL AFU Error "
-					    "undelivered to pe %i: %.llx\n",
+					    "undelivered to pe %i: 0x%016llx\n",
 					    ctx->pe, irq_info->afu_err);
 		} else {
 			spin_lock(&ctx->lock);
@@ -211,8 +211,8 @@ static irqreturn_t cxl_irq_multiplexed(int irq, void *data)
 	}
 	rcu_read_unlock();
 
-	WARN(1, "Unable to demultiplex CXL PSL IRQ for PE %i DSISR %.16llx DAR"
-		" %.16llx\n(Possible AFU HW issue - was a term/remove acked"
+	WARN(1, "Unable to demultiplex CXL PSL IRQ for PE %i DSISR %016llx DAR"
+		" %016llx\n(Possible AFU HW issue - was a term/remove acked"
 		" with outstanding transactions?)\n", ph, irq_info.dsisr,
 		irq_info.dar);
 	return fail_psl_irq(afu, &irq_info);
@@ -341,6 +341,9 @@ int cxl_register_psl_err_irq(struct cxl *adapter)
 
 void cxl_release_psl_err_irq(struct cxl *adapter)
 {
+	if (adapter->err_virq != irq_find_mapping(NULL, adapter->err_hwirq))
+		return;
+
 	cxl_p1_write(adapter, CXL_PSL_ErrIVTE, 0x0000000000000000);
 	cxl_unmap_irq(adapter->err_virq, adapter);
 	cxl_release_one_irq(adapter, adapter->err_hwirq);
@@ -374,6 +377,9 @@ int cxl_register_serr_irq(struct cxl_afu *afu)
 
 void cxl_release_serr_irq(struct cxl_afu *afu)
 {
+	if (afu->serr_virq != irq_find_mapping(NULL, afu->serr_hwirq))
+		return;
+
 	cxl_p1n_write(afu, CXL_PSL_SERR_An, 0x0000000000000000);
 	cxl_unmap_irq(afu->serr_virq, afu);
 	cxl_release_one_irq(afu->adapter, afu->serr_hwirq);
@@ -400,12 +406,15 @@ int cxl_register_psl_irq(struct cxl_afu *afu)
 
 void cxl_release_psl_irq(struct cxl_afu *afu)
 {
+	if (afu->psl_virq != irq_find_mapping(NULL, afu->psl_hwirq))
+		return;
+
 	cxl_unmap_irq(afu->psl_virq, afu);
 	cxl_release_one_irq(afu->adapter, afu->psl_hwirq);
 	kfree(afu->psl_irq_name);
 }
 
-void afu_irq_name_free(struct cxl_context *ctx)
+static void afu_irq_name_free(struct cxl_context *ctx)
 {
 	struct cxl_irq_name *irq_name, *tmp;
 
@@ -421,6 +430,9 @@ int afu_allocate_irqs(struct cxl_context *ctx, u32 count)
 	int rc, r, i, j = 1;
 	struct cxl_irq_name *irq_name;
 
+	/* Initialize the list head to hold irq names */
+	INIT_LIST_HEAD(&ctx->irq_names);
+
 	if ((rc = cxl_alloc_irq_ranges(&ctx->irqs, ctx->afu->adapter, count)))
 		return rc;
 
@@ -432,13 +444,12 @@ int afu_allocate_irqs(struct cxl_context *ctx, u32 count)
 	ctx->irq_bitmap = kcalloc(BITS_TO_LONGS(count),
 				  sizeof(*ctx->irq_bitmap), GFP_KERNEL);
 	if (!ctx->irq_bitmap)
-		return -ENOMEM;
+		goto out;
 
 	/*
 	 * Allocate names first.  If any fail, bail out before allocating
 	 * actual hardware IRQs.
 	 */
-	INIT_LIST_HEAD(&ctx->irq_names);
 	for (r = 1; r < CXL_IRQ_RANGES; r++) {
 		for (i = 0; i < ctx->irqs.range[r]; i++) {
 			irq_name = kmalloc(sizeof(struct cxl_irq_name),
@@ -460,11 +471,12 @@ int afu_allocate_irqs(struct cxl_context *ctx, u32 count)
 	return 0;
 
 out:
+	cxl_release_irq_ranges(&ctx->irqs, ctx->afu->adapter);
 	afu_irq_name_free(ctx);
 	return -ENOMEM;
 }
 
-void afu_register_hwirqs(struct cxl_context *ctx)
+static void afu_register_hwirqs(struct cxl_context *ctx)
 {
 	irq_hw_number_t hwirq;
 	struct cxl_irq_name *irq_name;
@@ -511,4 +523,8 @@ void afu_release_irqs(struct cxl_context *ctx, void *cookie)
 
 	afu_irq_name_free(ctx);
 	cxl_release_irq_ranges(&ctx->irqs, ctx->afu->adapter);
+
+	kfree(ctx->irq_bitmap);
+	ctx->irq_bitmap = NULL;
+	ctx->irq_count = 0;
 }
diff --git a/drivers/misc/cxl/main.c b/drivers/misc/cxl/main.c
index 4a164ab8b35a..9fde75ed4fac 100644
--- a/drivers/misc/cxl/main.c
+++ b/drivers/misc/cxl/main.c
@@ -222,6 +222,7 @@ static void exit_cxl(void)
 	cxl_debugfs_exit();
 	cxl_file_exit();
 	unregister_cxl_calls(&cxl_calls);
+	idr_destroy(&cxl_adapter_idr);
 }
 
 module_init(init_cxl);
diff --git a/drivers/misc/cxl/native.c b/drivers/misc/cxl/native.c
index 10567f245818..b37f2e8004f5 100644
--- a/drivers/misc/cxl/native.c
+++ b/drivers/misc/cxl/native.c
@@ -41,7 +41,14 @@ static int afu_control(struct cxl_afu *afu, u64 command,
 			rc = -EBUSY;
 			goto out;
 		}
-		pr_devel_ratelimited("AFU control... (0x%.16llx)\n",
+
+		if (!cxl_adapter_link_ok(afu->adapter)) {
+			afu->enabled = enabled;
+			rc = -EIO;
+			goto out;
+		}
+
+		pr_devel_ratelimited("AFU control... (0x%016llx)\n",
 				     AFU_Cntl | command);
 		cpu_relax();
 		AFU_Cntl = cxl_p2n_read(afu, CXL_AFU_Cntl_An);
@@ -85,6 +92,10 @@ int __cxl_afu_reset(struct cxl_afu *afu)
 
 int cxl_afu_check_and_enable(struct cxl_afu *afu)
 {
+	if (!cxl_adapter_link_ok(afu->adapter)) {
+		WARN(1, "Refusing to enable afu while link down!\n");
+		return -EIO;
+	}
 	if (afu->enabled)
 		return 0;
 	return afu_enable(afu);
@@ -103,6 +114,12 @@ int cxl_psl_purge(struct cxl_afu *afu)
 
 	pr_devel("PSL purge request\n");
 
+	if (!cxl_adapter_link_ok(afu->adapter)) {
+		dev_warn(&afu->dev, "PSL Purge called with link down, ignoring\n");
+		rc = -EIO;
+		goto out;
+	}
+
 	if ((AFU_Cntl & CXL_AFU_Cntl_An_ES_MASK) != CXL_AFU_Cntl_An_ES_Disabled) {
 		WARN(1, "psl_purge request while AFU not disabled!\n");
 		cxl_afu_disable(afu);
@@ -119,14 +136,19 @@ int cxl_psl_purge(struct cxl_afu *afu)
 			rc = -EBUSY;
 			goto out;
 		}
+		if (!cxl_adapter_link_ok(afu->adapter)) {
+			rc = -EIO;
+			goto out;
+		}
+
 		dsisr = cxl_p2n_read(afu, CXL_PSL_DSISR_An);
-		pr_devel_ratelimited("PSL purging... PSL_CNTL: 0x%.16llx  PSL_DSISR: 0x%.16llx\n", PSL_CNTL, dsisr);
+		pr_devel_ratelimited("PSL purging... PSL_CNTL: 0x%016llx  PSL_DSISR: 0x%016llx\n", PSL_CNTL, dsisr);
 		if (dsisr & CXL_PSL_DSISR_TRANS) {
 			dar = cxl_p2n_read(afu, CXL_PSL_DAR_An);
-			dev_notice(&afu->dev, "PSL purge terminating pending translation, DSISR: 0x%.16llx, DAR: 0x%.16llx\n", dsisr, dar);
+			dev_notice(&afu->dev, "PSL purge terminating pending translation, DSISR: 0x%016llx, DAR: 0x%016llx\n", dsisr, dar);
 			cxl_p2n_write(afu, CXL_PSL_TFC_An, CXL_PSL_TFC_An_AE);
 		} else if (dsisr) {
-			dev_notice(&afu->dev, "PSL purge acknowledging pending non-translation fault, DSISR: 0x%.16llx\n", dsisr);
+			dev_notice(&afu->dev, "PSL purge acknowledging pending non-translation fault, DSISR: 0x%016llx\n", dsisr);
 			cxl_p2n_write(afu, CXL_PSL_TFC_An, CXL_PSL_TFC_An_A);
 		} else {
 			cpu_relax();
@@ -161,10 +183,8 @@ static int spa_max_procs(int spa_size)
 	return ((spa_size / 8) - 96) / 17;
 }
 
-static int alloc_spa(struct cxl_afu *afu)
+int cxl_alloc_spa(struct cxl_afu *afu)
 {
-	u64 spap;
-
 	/* Work out how many pages to allocate */
 	afu->spa_order = 0;
 	do {
@@ -183,6 +203,13 @@ static int alloc_spa(struct cxl_afu *afu)
 	pr_devel("spa pages: %i afu->spa_max_procs: %i   afu->num_procs: %i\n",
 		 1<<afu->spa_order, afu->spa_max_procs, afu->num_procs);
 
+	return 0;
+}
+
+static void attach_spa(struct cxl_afu *afu)
+{
+	u64 spap;
+
 	afu->sw_command_status = (__be64 *)((char *)afu->spa +
 					    ((afu->spa_max_procs + 3) * 128));
 
@@ -191,14 +218,19 @@ static int alloc_spa(struct cxl_afu *afu)
 	spap |= CXL_PSL_SPAP_V;
 	pr_devel("cxl: SPA allocated at 0x%p. Max processes: %i, sw_command_status: 0x%p CXL_PSL_SPAP_An=0x%016llx\n", afu->spa, afu->spa_max_procs, afu->sw_command_status, spap);
 	cxl_p1n_write(afu, CXL_PSL_SPAP_An, spap);
-
-	return 0;
 }
 
-static void release_spa(struct cxl_afu *afu)
+static inline void detach_spa(struct cxl_afu *afu)
 {
 	cxl_p1n_write(afu, CXL_PSL_SPAP_An, 0);
-	free_pages((unsigned long) afu->spa, afu->spa_order);
+}
+
+void cxl_release_spa(struct cxl_afu *afu)
+{
+	if (afu->spa) {
+		free_pages((unsigned long) afu->spa, afu->spa_order);
+		afu->spa = NULL;
+	}
 }
 
 int cxl_tlb_slb_invalidate(struct cxl *adapter)
@@ -215,6 +247,8 @@ int cxl_tlb_slb_invalidate(struct cxl *adapter)
 			dev_warn(&adapter->dev, "WARNING: CXL adapter wide TLBIA timed out!\n");
 			return -EBUSY;
 		}
+		if (!cxl_adapter_link_ok(adapter))
+			return -EIO;
 		cpu_relax();
 	}
 
@@ -224,6 +258,8 @@ int cxl_tlb_slb_invalidate(struct cxl *adapter)
 			dev_warn(&adapter->dev, "WARNING: CXL adapter wide SLBIA timed out!\n");
 			return -EBUSY;
 		}
+		if (!cxl_adapter_link_ok(adapter))
+			return -EIO;
 		cpu_relax();
 	}
 	return 0;
@@ -240,6 +276,11 @@ int cxl_afu_slbia(struct cxl_afu *afu)
 			dev_warn(&afu->dev, "WARNING: CXL AFU SLBIA timed out!\n");
 			return -EBUSY;
 		}
+		/* If the adapter has gone down, we can assume that we
+		 * will PERST it and that will invalidate everything.
+		 */
+		if (!cxl_adapter_link_ok(afu->adapter))
+			return -EIO;
 		cpu_relax();
 	}
 	return 0;
@@ -279,6 +320,8 @@ static void slb_invalid(struct cxl_context *ctx)
 	cxl_p1_write(adapter, CXL_PSL_SLBIA, CXL_TLB_SLB_IQ_LPIDPID);
 
 	while (1) {
+		if (!cxl_adapter_link_ok(adapter))
+			break;
 		slbia = cxl_p1_read(adapter, CXL_PSL_SLBIA);
 		if (!(slbia & CXL_TLB_SLB_P))
 			break;
@@ -308,6 +351,11 @@ static int do_process_element_cmd(struct cxl_context *ctx,
 			rc = -EBUSY;
 			goto out;
 		}
+		if (!cxl_adapter_link_ok(ctx->afu->adapter)) {
+			dev_warn(&ctx->afu->dev, "WARNING: Device link down, aborting Process Element Command!\n");
+			rc = -EIO;
+			goto out;
+		}
 		state = be64_to_cpup(ctx->afu->sw_command_status);
 		if (state == ~0ULL) {
 			pr_err("cxl: Error adding process element to AFU\n");
@@ -355,8 +403,13 @@ static int terminate_process_element(struct cxl_context *ctx)
 
 	mutex_lock(&ctx->afu->spa_mutex);
 	pr_devel("%s Terminate pe: %i started\n", __func__, ctx->pe);
-	rc = do_process_element_cmd(ctx, CXL_SPA_SW_CMD_TERMINATE,
-				    CXL_PE_SOFTWARE_STATE_V | CXL_PE_SOFTWARE_STATE_T);
+	/* We could be asked to terminate when the hw is down. That
+	 * should always succeed: it's not running if the hw has gone
+	 * away and is being reset.
+	 *